© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260275
    Prev
    Next
    INDEX
    Explanations

    returns tuple:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $).
    0.27
    roft
    0.26
    uí
    0.25
    „
    0.25
    re
    0.25
    ro
    0.25
    ow
    0.24
    vita
    0.24
    renderSquare
    0.24
    Estamos
    0.24
    POSITIVE LOGITS
     ওসমান
    0.27
     validate
    0.26
     rahul
    0.26
    的问题
    0.26
     valg
    0.26
     Simons
    0.25
    ધાનસભા
    0.25
     মুহাম্ম
    0.25
    㭐
    0.25
     newVal
    0.25
    Activations Density 0.000%

    No Known Activations